Study compares adaptive vs fixed query learning methods.
problem Comparing adaptive and fixed query learning methods for task approximation.
method Examined in-context and agentic learning in two settings: unrestricted and realizable.
result Adaptivity does not hinder performance in unrestricted setting but can in realizable setting.
In this paper, we propose a generic framework for devising an adaptive approximation scheme for value function approximation in reinforcement learning, which introduces multiscale approximation. The two basic ingredients are multiresolution analysis as well as tree approximation. Starting from simple refinable function…
Adaptive approximations improve variational inference for complex models.
problem Efficiently approximate marginal distributions and partition functions in complex probabilistic models.
method Two classes of adaptive approximations that include Bethe, tree-reweighted, and convex free energies.
result Proposed approximations automatically adapt to a given model and outperform existing methods.
New algorithm reduces interventional strategy complexity for causal graph discovery.
problem Designing efficient interventional strategies for causal graph discovery.
method Developed an r-adaptive algorithm for causal graph discovery that minimizes the number of interventions.
result Achieved an approximation of O(min{r, log n} * n^{1/min{r, log n}}) for the verification number.
Adaptive neural network approximates stochastic system densities.
problem Approximating high-dimensional stochastic dynamical systems.
method Temporal KRnet (tKRnet) trained with adaptive collocation points and temporal decomposition.
result Improves density approximation for stochastic systems without curse of dimensionality.
New Hermite approximations accelerate convergence with adaptive coordinate transformations.
problem Accelerating convergence of spectral approximations for Hermite expansions.
method Using normalizing flows for adaptive coordinate transformations and deriving error estimates.
result Error estimates for Hermite expansions under adaptive coordinate transformations.
New guarantees for adaptive combinatorial maximization with various objectives.
problem Maximizing under cardinality constraints and minimum cost coverage in adaptive settings.
method Bayesian approach with comprehensive approximation guarantees for various utility functions.
result Maximal gain ratio is a new parameter that provides stronger approximation guarantees than greedy policies.
Adaptive reduction scheme approximates optimal policy in regularized MDPs.
problem Finding near optimal policy in regularized MDPs with biased solutions.
method Adaptive reduction of regularization parameter λ to approximate optimal policy.
result Iteration complexity reduced for obtaining ε-optimal policy.
Fast algorithms developed for adaptive and fully adaptive submodular maximization problems.
problem Maximizing submodular functions subject to constraints in linear time.
method Developed linear-time algorithms for two submodular maximization problems: adaptive and fully adaptive.
result Achieved (1−1/e−ε) approximation ratio for adaptive submodular maximization and $ rac{1-1/e-ε}{4-2/e-2ε}$ for fully adaptive submodular maximization. Paper presents a Transformer model for automatic domain adaptation.
problem Challenges in selecting or designing domain adaptation algorithms.
method Transformer model approximates and selects domain adaptation algorithms.
result Transformers can approximate and automatically select domain adaptation algorithms.
New algorithm maximizes non-monotone adaptive submodular functions in linear time.
problem Maximizing non-monotone adaptive submodular functions subject to a cardinality constraint.
method Developed a linear-time algorithm for non-monotone adaptive submodular maximization.
result Achieved a 1/e−ε approximation ratio with O(nε−2logε−1) value oracle queries. We propose a new concept named adaptive submodularity ratio to study the greedy policy for sequential decision making. While the greedy policy is known to perform well for a wide variety of adaptive stochastic optimization problems in practice, its theoretical properties have been analyzed only for a limited class of p…
Paper proposes adaptive control for unknown systems using reinforcement learning.
problem Adaptive control for unknown, linearizable systems.
method On-policy reinforcement learning for discrete-time, stochastic systems.
result Stability and tracking errors concentrate near zero with high probability.
ADDA-KR uses KRnets for solving high-dimensional Fokker-Planck equations.
problem High-dimensional, unbounded Fokker-Planck equations.
method KRnet for density approximation, adaptive sampling for stochastic collocation.
result ADDA-KR efficiently approximates high-dimensional density functions.
Adaptive sequential decision making is one of the central challenges in machine learning and artificial intelligence. In such problems, the goal is to design an interactive policy that plans for an action to take, from a finite set of n actions, given some partial observations. It has been shown that in many applicat…
We consider Bayesian inference problems with computationally intensive likelihood functions. We propose a Gaussian process (GP) based method to approximate the joint distribution of the unknown parameters and the data. In particular, we write the joint density approximately as a product of an approximate posterior dens…
LaLoRA prevents forgetting in LoRA fine-tuning.
problem Catastrophic forgetting in fine-tuned models.
method LaLoRA applies Laplace approximation to LoRA weights for regularization.
result Improved learning-forgetting trade-off with controllable regularization strength.
Consider the problem: given the data pair (x,y) drawn from a population with f∗(x)=E[y∣x=x], specify a neural network model and run gradient flow on the weights over time until reaching any stationarity. How does ft, the function computed by the neural network…
Deep networks adapt to function regularity and data distribution.
problem Understanding deep learning's adaptability to function regularity and data distribution.
method Developed nonparametric approximation and estimation theories for a broad class of functions using deep ReLU networks.
result Deep neural networks are adaptive to different regularity of functions and nonuniform data distributions.
We consider the problem of efficiently approximating and encoding high-dimensional data sampled from a probability distribution ρ in RD, that is nearly supported on a d-dimensional set M - for example supported on a d-dimensional Riemannian manifold. Geometric Multi-Resolution Analysis (GM…
Adaptive Multilevel Monte Carlo improves probability estimation for complex random variables.
problem Estimating probabilities of complex random variables with multiple approximations.
method Adaptive Multilevel Monte Carlo framework for discontinuous functionals.
result Achieves optimal computational complexities for both smooth and discontinuous functionals.
New MCMC algorithm reduces subset selection passes to 2 for optimal k-dimensional subspace approximation.
problem Subset selection for k-dimensional subspace approximation with ε-approximation. method MCMC sampling algorithm reducing passes to 2 for p=2 case, poly(k/ε) size subset. result Subset selection of nearly optimal size in 2 passes, (1+ε) approximation. Adapting functional gradients improves FGD's practicality and theoretical guarantees.
problem Implementing FGD in practice due to infinite-dimensional functional gradients.
method Adapting the representation of functional gradients.
result Establishes convergence to a stationary point for smooth losses and a global minimizer under smoothness + Polyak-Lojasiewicz condition.
We analyze the computational limits of LoRA for transformer models using fine-grained complexity theory.
problem Computational efficiency of LoRA fine-tuning for transformer models.
method Fine-grained complexity theory, identifying phase transitions, almost linear algorithms.
result Existence of almost linear algorithms for LoRA adaptation based on specific norms.
New algorithms improve causal graph discovery with adaptive interventions, even under worst-case interventional costs.
problem Discover causal relationships from data with adaptive interventions and node-dependent costs.
method Define new benchmarks and provide adaptive search algorithms for causal graph discovery.
result Logarithmic approximations achieved under various settings: atomic, bounded size interventions and generalized cost objectives.
Unified framework for sampling and approximating high-dimensional energy landscapes.
problem Sampling and approximating complex energy landscapes in physical systems with constraints and energy barriers.
method Formulates a minimax optimization problem that jointly adapts surrogate approximation and adaptive sampling.
result Demonstrates effectiveness in biomolecular systems with up to 30 collective variables.
Improved multilevel scheme for value-at-risk computation.
problem Discontinuity in Heaviside function affects value-at-risk computation.
method Adaptive multilevel stochastic approximation to mitigate discontinuity.
result Best complexity improved to O(ε−2∣lnε∣25). Model-free reinforcement learning algorithms combined with value function approximation have recently achieved impressive performance in a variety of application domains. However, the theoretical understanding of such algorithms is limited, and existing results are largely focused on episodic or discounted Markov decis…
LoRA enhances model adaptability without increasing parameters.
problem Theoretical understanding of LoRA's adaptability.
method Theoretical analysis of LoRA's expressive power.
result LoRA can adapt any model to a smaller target model with a specific rank.
When using reinforcement learning (RL) algorithms it is common, given a large state space, to introduce some form of approximation architecture for the value function (VF). The exact form of this architecture can have a significant effect on an agent's performance, however, and determining a suitable approximation arch…
Paper proposes SRA algorithm for online learning robustness and adaptivity.
problem Quantifying and evaluating tradeoff between robustness and adaptivity in online learning.
method SRA algorithm using biased stochastic approximation scheme with adaptive threshold.
result SRA algorithm provides superior performance in synthetic and real datasets.
AIS algorithm improves heavy-tailed distribution estimation.
problem Inconsistent estimators and slow convergence in AIS for heavy-tailed distributions.
method Adapts Student-t proposal distributions by matching escort moments and minimizing α-divergence.
result Improves estimation accuracy for heavy-tailed distributions.
Adaptive learning rate algorithms such as RMSProp are widely used for training deep neural networks. RMSProp offers efficient training since it uses first order gradients to approximate Hessian-based preconditioning. However, since the first order gradients include noise caused by stochastic optimization, the approxima…
A framework isolates and learns approximately shared features for better domain adaptation.
problem Reducing performance degradation in unseen domains using machine learning models.
method Statistical framework distinguishing feature utilities based on correlation variance across domains. Learning approximately shared features from source tasks and fine-tuning on target tasks.
result Improved population risk compared to previous results on both source and target tasks, resolving the paradox of feature selection.
We develop a generalization of manifold calculus in the sense of Goodwillie-Weiss where the manifold is replaced by a simplicial complex. We consider functors from the category of open subsets of a fixed simplical complex into the category of topological spaces and prove an analogue of the approximation theorem. Namely…
Study improves BN TTA under distribution shift using higher-order asymptotics.
problem Improving BN TTA for changing data distributions.
method Integrates Edgeworth expansion and saddlepoint approximation with one-step M-estimation.
result Derives optimal weighting parameter for minimized mean-squared error.
DALTON improves ODE parameter estimation by learning from noisy data.
problem High sensitivity to parameters in ODEs produces unreliable parameter estimates.
method Data-adaptive probabilistic likelihood approximation for ODEs.
result DALTON produces more accurate parameter estimates than existing methods.
CoLoRA models predict PDE solutions quickly and accurately with minimal data.
problem Efficiently modeling PDE solutions with limited data.
method Continuous low-rank adaptation of neural networks trained on offline data.
result Predictions are orders of magnitude faster and more accurate than classical methods.
Efficient RL algorithms for linear function approximation with limited adaptivity constraints.
problem Limited adaptivity in reinforcement learning with linear function approximation.
method Proposed two efficient online RL algorithms for episodic linear Markov decision processes under batch learning and rare policy switch models.
result Achieved efficient regret bounds for both batch learning and rare policy switch models, with substantial reduction in adaptivity.
New adaptive stepsize method for stochastic approximation converges to target point.
problem Finding optimal step sizes for stochastic approximation algorithms.
method Adaptive block-coordinate stepsizes using online estimates of second moment.
result New method converges almost surely to a small neighborhood of the target point.
Adaptive operator learning reduces costs in Bayesian inverse problems.
problem Reducing computational costs in Bayesian inverse problems governed by PDEs.
method Adaptive operator learning framework that gradually reduces modeling error.
result The approach significantly reduces computational costs while maintaining inversion accuracy.
Paper proposes Nyström sketches for better adaptive compressive learning.
problem Improving adaptability of sketching for compressive learning.
method Data-dependent Nyström approximation for mean embedding.
result Excess risk can be controlled with geometric assumption.
DAS-PINNs uses deep learning to solve complex PDEs more accurately.
problem Solving high-dimensional PDEs with high accuracy.
method Deep neural networks and generative models for adaptive sampling.
result DAS-PINNs significantly improves solution accuracy for low regularity and high-dimensional problems.
Adaptive optimal control using value iteration initiated from a stabilizing control policy is theoretically analyzed in terms of stability of the system during the learning stage without ignoring the effects of approximation errors. This analysis includes the system operated using any single/constant resulting control …
We address the issue of knots selection for Gaussian predictive process methodology. Predictive process approximation provides an effective solution to the cubic order computational complexity of Gaussian process models. This approximation crucially depends on a set of points, called knots, at which the original proces…
Smooth activations enable optimal error rates in neural networks for Sobolev function classes.
problem Achieving optimal approximation and estimation error rates for neural networks in Sobolev function classes.
method Study of neural networks with smooth activations, proving optimal rates via approximation and statistical properties.
result Constant-depth networks with smooth activations achieve optimal rates of approximation and estimation, demonstrating smoothness adaptivity.
Enhanced DFO using adaptive batch-based FD estimates.
problem Derivative-free optimization with imprecise gradient estimates.
method Adaptive batch-based finite difference estimation and dynamic sampling strategy.
result Algorithm achieves convergence rate similar to KW and SPSA methods.
Bayesian neural networks approximate Gaussian, this method adapts to non-Gaussian posteriors.
problem Bayesian neural networks struggle with non-Gaussian posteriors, leading to poor performance.
method Proposes a Riemannian Laplace approximation to adapt to the shape of the true posterior.
result Consistently improves over conventional Laplace approximation across tasks.